Pharmacogenomics J. 2025 Feb 19;25(2):2. doi: 10.1038/s41397-025-00361-6.

ABSTRACT

The pathogenesis of cancer is complicated, and different types of cancer often exhibit different gene mutations resulting in different omics profiles. The purpose of this study was to systematically identify cancer-specific biological pathways and potential cancer-targeting drugs. We collectively analyzed the transcriptomics and proteomics data from 16 common types of human cancer to study the mechanism of carcinogenesis and seek potential treatment. Statistical approaches were applied to identify significant molecular targets and pathways related to each cancer type. Potential anti-cancer drugs were subsequently retrieved that can target these pathways. The number of significant pathways linked to each cancer type ranged from four (stomach cancer) to 112 (acute myeloid leukemia), and the number of therapeutic drugs that can target these cancer related pathways, ranged from one (ovarian cancer) to 97 (acute myeloid leukemia and non-small-cell lung carcinoma). As a validation of our method, some of these drugs are FDA approved therapies for their corresponding cancer type. Our findings provide a rich source of testable hypotheses that can be applied to deconvolute the complex underlying mechanisms of human cancer and used to prioritize and repurpose drugs as anti-cancer therapies.

PMID:39971899 | DOI:10.1038/s41397-025-00361-6

Basic Clin Pharmacol Toxicol. 2025 Mar;136(3):e70009. doi: 10.1111/bcpt.70009.

ABSTRACT

Precision medicine has significantly advanced through the development of predictive biomarkers based on pharmacogenetic (PGx) testing. These tests identify interactions between drugs and genetic variants that influence patient responses to treatments. Understanding genetic variations in drug-metabolizing enzymes, receptors and transporters and their impact on pharmacokinetics and pharmacodynamics allows for the prediction of drug effects and side effects, enabling tailored treatments for different patient groups. This review focuses on drugs metabolized by cytochrome P450 (CYP450) enzymes, for example, citalopram and clopidogrel or transported by the solute carrier organic anion transporter family member 1B1 (SLCO1B1), for example, atorvastatin and simvastatin, with PGx dosing guidelines, in the context of consumption in Scandinavian countries. A major barrier to the widespread adoption of PGx tests in clinical practice has been healthcare professionals' uncertainty about their efficacy, complexity in result interpretation and questions regarding the evidence base. However, recent studies have demonstrated PGx testing has the potential to improve treatment outcomes, reduce adverse drug reactions and achieve cost savings. These findings underscore the potential of PGx testing as a valuable tool in clinical decision making, promoting its use in a pre-emptive manner to enhance patient care.

PMID:39971612 | DOI:10.1111/bcpt.70009

QJM. 2025 Feb 20:hcaf035. doi: 10.1093/qjmed/hcaf035. Online ahead of print.

ABSTRACT

BACKGROUND: Variation in DNA is known to contribute to medication response, impacting both medicine effectiveness and incidence of adverse drug reactions (ADRs). However, clinical implementation of pharmacogenomics (PGx) has been slow, and the views of the public are not well understood.

AIM: To assess UK national public attitudes around pharmacogenetics.

DESIGN AND METHODS: The survey was co-designed with the Participant Panel at Genomics England and the data were collected by the National Centre for Social Research, using its nationally representative panel of UK adults. Multivariable logistic regression analyses were used to analyse relationships between selected survey reported variables, controlled for age and sex.

RESULTS: The survey response rate was 58%. Two thousand seven hundred and nineteen responses were obtained. Most respondents (59%) had experienced either no benefit or a side effect. Forty-five per cent of respondents reported having experienced no benefit and 46% of respondents reported having experienced a side effect, with female respondents more likely to be in both groups (P < 0.0001). Despite variability in interindividual medicine response being well understood (89%), the involvement of DNA in predicting benefit or risk of a side effect is not (understood by 52% and 48%, respectively). Eighty-nine per cent would complete a PGx test, with 91% wanting direct access to this information. Eighty-five per cent of UK adults think that the NHS should offer PGx to those regularly taking many medicines. Respondents were not more worried overall about misuse of PGx data compared with other routine medical data. Experience with prescription medication impacted on views with those who were prescribed medication almost twice as likely to want a PGx test for any reason.

CONCLUSION: Most respondents reported experience with either a medication not working for them or ADRs. There was a high level of understanding of variable medication response but a relatively low level of awareness of the role genetics plays in that variability. Most respondents would want a PGx test, to have direct access to results, and think the NHS should offer this form of testing. Importantly, respondents were not more concerned about PGx data use than that of any other routinely generated medical data. Notably, this study highlights a relationship between individuals' experiences with prescription medications and their interest in PGx testing, underscoring the potential for personalized medicine to address public healthcare needs.

PMID:39971322 | DOI:10.1093/qjmed/hcaf035

Prog Neuropsychopharmacol Biol Psychiatry. 2025 Feb 17:111292. doi: 10.1016/j.pnpbp.2025.111292. Online ahead of print.

ABSTRACT

Response to antidepressants (ADs) is highly variable and partly genetically driven, but the utility of pharmacogenetic testing in guiding ADs treatment is still controversial. We conducted a retrospective, naturalistic study to explore the utility of CYP2C6 and CYP2C19 genotyping in ADs treatment in a sample of 156 patients diagnosed with major depressive disorder from South Sardinia (Italy). Clinical data, including history of medication regimens, adverse reactions, and response to ADs, were collected over the last five years preceding recruitment. Patients received pharmacogenetic testing at recruitment and were classified depending on whether their history of treatment regimen followed the recommendations of the Clinical Pharmacogenetics Implementation Consortium (CPIC)). Non-responders to ADs had a larger number of therapeutic regimens and of medication changes due to lack of response compared to responders. Patients with at least one incongruent regimen had a larger number of total therapeutic changes and fewer congruent regimens. Metabolizing phenotypes of CYP2D6 were not associated with response to ADs or changes in regimen of any kind. However, the group of ultra-rapid metabolizers for CYP2C19 showed significantly smaller improvement in symptoms while the poor-metabolizers showed a larger number of medication changes for side effects compared to normal, intermediate and rapid metabolizers. Our findings suggest that the implementation of pharmacogenetic testing based on CYP2C19 could be clinically useful in guiding AD treatment, but further studies are warranted to investigate the clinical implications of implementing PGx testing in depression.

PMID:39971121 | DOI:10.1016/j.pnpbp.2025.111292

Benef Microbes. 2025 Feb 12:1-14. doi: 10.1163/18762891-bja00058. Online ahead of print.

ABSTRACT

Faecalibacterium is an essential probiotic in the human gut; changes in its abundance are associated with various disease states in many studies. However, the causal nature of such associations remains obscure. Therefore, we aimed to thoroughly investigate the causal relationships between Faecalibacterium and its related diseases. A two-sample bi-directional Mendelian randomisation analysis was conducted using publicly available genome-wide association studies summary statistics for Faecalibacterium and its related diseases. We found that Faecalibacterium was negatively correlated with the risk of ankylosing spondylitis (odds ratio [OR] = 0.526, 95% confidence interval [CI]:0.304-0.908, P = 0.021), atopic dermatitis (OR = 0.484, 95%CI: 0.261-0.898, P = 0.021) and heart failure (OR = 0.657, 95%CI: 0.467-0.924, P = 0.016), while Faecalibacterium was positively associated with autism spectrum disorder risk (OR = 2.529, 95%CI: 1.012-6.319, P = 0.047). The results of reverse Mendelian randomisation analysis showed that acute sinusitis (OR = 0.902, 95%CI: 0.839-0.970, P = 0.005) and Alzheimer's disease (OR = 0.976, 95%CI: 0.958-0.993, P = 0.008) was causally associated with lower Faecalibacterium abundance, respectively, while cirrhosis (OR = 1.154, 95%CI: 1.028-1.295, P = 0.015) and multiple myeloma (OR = 2.619 × 1012, 95%CI: 2.492-2.754 × 1024, P = 0.043) was causally associated with higher Faecalibacterium abundance. Our findings firstly showed that changes in Faecalibacterium abundance may contribute to the risk of ankylosing spondylitis, atopic dermatitis, heart failure and autism spectrum disorders, and potentially as a result of acute sinusitis, Alzheimer's disease, cirrhosis and multiple myeloma.

PMID:39970929 | DOI:10.1163/18762891-bja00058

Nat Rev Cardiol. 2025 Feb 19. doi: 10.1038/s41569-025-01130-5. Online ahead of print.

ABSTRACT

Ageing of the cardiovascular system is associated with frailty and various life-threatening diseases. As global populations grow older, age-related conditions increasingly determine healthspan and lifespan. The circulatory system not only supplies nutrients and oxygen to all tissues of the human body and removes by-products but also builds the largest interorgan communication network, thereby serving as a gatekeeper for healthy ageing. Therefore, elucidating organ-specific and cell-specific ageing mechanisms that compromise circulatory system functions could have the potential to prevent or ameliorate age-related cardiovascular diseases. In support of this concept, emerging evidence suggests that targeting the circulatory system might restore organ function. In this Roadmap, we delve into the organ-specific and cell-specific mechanisms that underlie ageing-related changes in the cardiovascular system. We raise unanswered questions regarding the optimal design of clinical trials, in which markers of biological ageing in humans could be assessed. We provide guidance for the development of gerotherapeutics, which will rely on the technological progress of the diagnostic toolbox to measure residual risk in elderly individuals. A major challenge in the quest to discover interventions that delay age-related conditions in humans is to identify molecular switches that can delay the onset of ageing changes. To overcome this roadblock, future clinical trials need to provide evidence that gerotherapeutics directly affect one or several hallmarks of ageing in such a manner as to delay, prevent, alleviate or treat age-associated dysfunction and diseases.

PMID:39972009 | DOI:10.1038/s41569-025-01130-5

Curr Gastroenterol Rep. 2025 Feb 19;27(1):14. doi: 10.1007/s11894-025-00959-7.

ABSTRACT

PURPOSE OF REVIEW: Common indications to evaluate exocrine pancreatic function in children include chronic diarrhea, steatorrhea, failure to thrive, cystic fibrosis and those with chronic abdominal pain due to chronic pancreatitis where imaging studies are normal [1]. Exocrine Pancreatic Insufficiency (EPI) has a spectrum of severity. In children often remains an underdiagnosed condition, particularly in its mild, partial, and isolated enzyme deficiency forms. The purpose of this review is to help understand the different varieties of EPI including isolated pancreatic enzyme deficiencies as possible causes of malnutrition and growth failure in pediatric patients.

RECENT FINDINGS: Among the indirect diagnostic methods, the fecal elastase-1 (FE-1) testing is the most widely used one. While it has good sensitivity and specificity in severe pancreatic damage, like cystic fibrosis in children, its performance in the diagnosis of mild, partial, and isolated enzyme deficiencies is poor. Direct pancreatic function testing performed during endoscopy (ePFT), has emerged as a more sensitive and specific method for assessing all forms of exocrine pancreatic function. Notably, recent guidelines from the North American Society for Pediatric Gastroenterology, Hepatology, and Nutrition (NASPGHAN) emphasize the importance of ePFT in pediatric patients. Most of the pediatric practitioners taught that the pancreas has only two diseases, cystic fibrosis and pancreatitis. They are missing the fact that pancreas, like other digestive organs, can have different, many times secondary, dysfunctions that influence the growth of children. Most pediatric gastroenterologists still use the fecal elastase-1 (FE-1) test, however, this lacks sufficient specificity and sensitivity [2-5] especially in patients with mild or early pancreatic disease or those with isolated enzyme deficiencies [5]. The most accurate diagnostic modality to explore these conditions is ePFT. In this review we highlighted the critical importance of direct pancreatic function testing. Enhancing clinical awareness and incorporating direct testing methods can ultimately improve outcomes for affected children.

PMID:39971805 | DOI:10.1007/s11894-025-00959-7

J Cyst Fibros. 2025 Feb 18:S1569-1993(25)00063-3. doi: 10.1016/j.jcf.2025.02.012. Online ahead of print.

ABSTRACT

The year 2024 marks a pivotal moment in the field of cystic fibrosis (CF) treatment, characterised by significant advancements in clinical care and an expanding body of literature on CF transmembrane conductance regulator (CFTR) modulators. These CFTR therapies have transformed the landscape of CF management, offered systemic benefits, and established new guidelines for assessing clinical manifestations and therapies. Additionally, progress has been made in newborn screening (NBS), diagnosis, and understanding outcomes for individuals with CF-related metabolic syndrome or inconclusive diagnostic results. However, amidst these clinical milestones, disparities in global access to CFTR modulators (CFTRm) persist, threatening to exacerbate existing inequities in CF care. This review provides a focused overview of the most impactful articles from 2024, highlighting both the clinical advancements and the pressing global accessibility challenges that define this transformative era in CF research and treatment.

PMID:39971692 | DOI:10.1016/j.jcf.2025.02.012

J Cyst Fibros. 2025 Feb 18:S1569-1993(25)00062-1. doi: 10.1016/j.jcf.2025.02.011. Online ahead of print.

ABSTRACT

BACKGROUND: AI-aided home stethoscopes offer the opportunity of continuous remote monitoring of cystic fibrosis (CF) patients, reducing the need for clinic visits.

AIM: This study aimed to analyze the possibility of detecting CF pulmonary exacerbations (PEx) at home using an AI-aided stethoscope (AIS).

MATERIALS AND METHODS: In a six-month study, 129 CF patients (85 children, 44 adults) used AIS for at least weekly self-examinations, recording various parameters: wheezes, rhonchi, crackles intensity, respiratory and heart rate, and inspiration-to-expiration ratio. Health state surveys were also completed. Physicians evaluated 5160 examinations to identify PEx. Machine learning models were trained using those parameters, and AUCs were calculated for PEx detection.

RESULTS: 522 self-examinations were diagnosed clinically as exacerbated. AI-aided home stethoscopes detected 415 exacerbated self-examinations (sensitivity 79.5 % at specificity 89.1 %). Among the single-parameter discriminators, coarse crackles intensity exhibited an AUC of 70 % (95% CI: 65-75) for young children, fine crackles intensity demonstrated an AUC of 75 % (95 % CI: 72-78) for older children, and an AUC of 93 % (95 % CI: 92-93) was achieved for adults using fine crackles intensity. The combination of parameters yielded the highest efficacy, with AUC exceeding 83% for objective parameters from the AI module alone and exceeding 90 % when incorporating both objective and subjective parameters across all groups.

CONCLUSIONS: The AI-aided home stethoscope has proven to be a reliable tool for detecting PEx with greater accuracy than self-assessment alone. Implementing this technology in healthcare systems has the potential to provide valuable insights for timely intervention and management of PExes.

PMID:39971691 | DOI:10.1016/j.jcf.2025.02.011

BMC Res Notes. 2025 Feb 19;18(1):77. doi: 10.1186/s13104-025-07142-1.

ABSTRACT

The nonlinear Telegraph equation appears in a variety of engineering and science problems. This paper presents a deep learning algorithm termed physics-informed neural networks to resolve a hyperbolic nonlinear telegraph equation with Dirichlet, Neumann, and Periodic boundary conditions. To include physical information about the issue, a multi-objective loss function consisting of the residual of the governing partial differential equation and initial conditions and boundary conditions is defined. Using multiple densely connected neural networks, termed feedforward deep neural networks, the proposed scheme has been trained to minimize the total loss results from the multi-objective loss function. Three computational examples are provided to demonstrate the efficacy and applications of our suggested method. Using a Python software package, we conducted several tests for various model optimizations, activation functions, neural network architectures, and hidden layers to choose the best hyper-parameters representing the problem's physics-informed neural network model with the optimal solution. Furthermore, using graphs and tables, the results of the suggested approach are contrasted with the analytical solution in literature based on various relative error analyses and statistical performance measure analyses. According to the results, the suggested computational method is effective in resolving difficult non-linear physical issues with various boundary conditions.

PMID:39972356 | DOI:10.1186/s13104-025-07142-1

Plant Methods. 2025 Feb 19;21(1):21. doi: 10.1186/s13007-025-01341-4.

ABSTRACT

Accurate detection of missed tassels is crucial for maintaining the purity of hybrid maize seed production. This study introduces the MT-YOLO model, designed to replace or assist manual detection by leveraging deep learning and unmanned aerial systems (UASs). A comprehensive dataset was constructed, informed by an analysis of the agronomic characteristics of missed tassels during the detasseling period, including factors such as tassel visibility, plant height variability, and tassel development stages. The dataset captures diverse tassel images under varying lighting conditions, planting densities, and growth stages, with special attention to early tasseling stages when tassels are partially wrapped in leaves-a critical yet underexplored challenge for accurate detasseling. The MT-YOLO model demonstrates significant improvements in detection metrics, achieving an average precision (AP) of 93.1%, precision of 93.3%, recall of 91.6%, and an F1-score of 92.4%, outperforming Faster R-CNN, SSD, and various YOLO models. Compared to the baseline YOLO v5s, the MT-YOLO model increased recall by 1.1%, precision by 4.9%, and F1-score by 3.0%, while maintaining a detection speed of 124 fps. Field tests further validated its robustness, achieving a mean missed rate of 9.1%. These results highlight the potential of MT-YOLO as a reliable and efficient solution for enhancing detasseling efficiency in hybrid maize seed production.

PMID:39972352 | DOI:10.1186/s13007-025-01341-4

Nature. 2025 Feb 19. doi: 10.1038/s41586-025-08598-8. Online ahead of print.

ABSTRACT

The recognition of ligands by transmembrane proteins is essential for the exchange of materials, energy and information across biological membranes. Progress has been made in the de novo design of transmembrane proteins1-6, as well as in designing water-soluble proteins to bind small molecules7-12, but de novo design of transmembrane proteins that tightly and specifically bind to small molecules remains an outstanding challenge13. Here we present the accurate design of ligand-binding transmembrane proteins by integrating deep learning and energy-based methods. We designed pre-organized ligand-binding pockets in high-quality four-helix backbones for a fluorogenic ligand, and generated a transmembrane span using gradient-guided hallucination. The designer transmembrane proteins specifically activated fluorescence of the target fluorophore with mid-nanomolar affinity, exhibiting higher brightness and quantum yield compared to those of enhanced green fluorescent protein. These proteins were highly active in the membrane fraction of live bacterial and eukaryotic cells following expression. The crystal and cryogenic electron microscopy structures of the designer protein-ligand complexes were very close to the structures of the design models. We showed that the interactions between ligands and transmembrane proteins within the membrane can be accurately designed. Our work paves the way for the creation of new functional transmembrane proteins, with a wide range of applications including imaging, ligand sensing and membrane transport.

PMID:39972138 | DOI:10.1038/s41586-025-08598-8

Sci Rep. 2025 Feb 19;15(1):6070. doi: 10.1038/s41598-025-90363-y.

ABSTRACT

This work introduces a novel method for estimating hydrological loading displacement using 3D Convolutional Neural Networks (3D-CNN). This approach utilizes vertical displacement time series data from 41 Global Navigation Satellite System (GNSS) stations across Yunnan Province, China, and its adjacent areas, coupled with spatiotemporal variations in terrestrial water storage derived from the Gravity Recovery and Climate Experiment satellites (GRACE). The 3D-CNN method demonstrates markedly higher inversion precision compared to conventional load Green's function inversion techniques. This improvement is evidenced by substantial reductions in deviations from GNSS observations across various statistical metrics: the maximum deviation decreased by 1.34 millimeters, the absolute minimum deviation by 1.47 millimeters, the absolute mean deviation by 79.6%, and the standard deviation by 31.4%. An in-depth analysis of terrestrial water storage and loading displacement from 2019 to 2022 in Yunnan Province revealed distinct seasonal fluctuations, primarily driven by dominant annual and semi-annual cycles, and these periodic signals accounted for over 90% of the variance. The spatial distribution of terrestrial water loading displacement is strongly associated with regional precipitation patterns, showing smaller amplitudes in the northeast and northwest and larger amplitudes in the southwest. The research findings presented in this paper offer a novel perspective on the spatiotemporal variations of environmental load effects, particularly those related to the terrestrial water loading deformation with significant spatial heterogeneity. Accurate assessment of the effects of terrestrial water loading displacement (TWLD) is of considerable importance for precise geodetic observations, as well as for the establishment and maintenance of high-precision dynamic reference frames. Furthermore, the development of TWLD model that integrates GRACE and GNSS data provides valuable data support for the higher-precision inversion of changes in terrestrial water storage.

PMID:39972111 | DOI:10.1038/s41598-025-90363-y

Sci Rep. 2025 Feb 19;15(1):6099. doi: 10.1038/s41598-025-89738-y.

ABSTRACT

Convolutional neural networks (CNNs) and mammalian visual systems share architectural and information processing similarities. We leverage these parallels to develop an in-silico CNN model simulating diseases affecting the visual system. This model aims to replicate neural complexities in an experimentally controlled environment. Therefore, we examine object recognition and internal representations of a CNN under neurodegeneration and neuroplasticity conditions simulated through synaptic weight decay and retraining. This approach can model neurodegeneration from events like tau accumulation, reflecting cognitive decline in diseases such as posterior cortical atrophy, a condition that can accompany Alzheimer's disease and primarily affects the visual system. After each degeneration iteration, we retrain unaffected synapses to simulate ongoing neuroplasticity. Our results show that with significant synaptic decay and limited retraining, the model's representational similarity decreases compared to a healthy model. Early CNN layers retain high similarity to the healthy model, while later layers are more prone to degradation. The results of this study reveal a progressive decline in object recognition proficiency, mirroring posterior cortical atrophy progression. In-silico modeling of neurodegenerative diseases can enhance our understanding of disease progression and aid in developing targeted rehabilitation and treatments.

PMID:39972104 | DOI:10.1038/s41598-025-89738-y

Sci Rep. 2025 Feb 19;15(1):6124. doi: 10.1038/s41598-025-90572-5.

ABSTRACT

This research presents a novel ensemble fuzzy deep learning approach for brain Magnetic Resonance Imaging (MRI) analysis, aiming to improve the segmentation of brain tissues and abnormalities. The method integrates multiple components, including diverse deep learning architectures enhanced with volumetric fuzzy pooling, a model fusion strategy, and an attention mechanism to focus on the most relevant regions of the input data. The process begins by collecting medical data using sensors to acquire MRI images. These data are then used to train several deep learning models that are specifically designed to handle various aspects of brain MRI segmentation. To enhance the model's performance, an efficient ensemble learning method is employed to combine the predictions of multiple models, ensuring that the final decision accounts for different strengths of each individual model. A key feature of the approach is the construction of a knowledge base that stores data from training images and associates it with the most suitable model for each specific sample. During the inference phase, this knowledge base is consulted to quickly identify and select the best model for processing new test images, based on the similarity between the test data and previously encountered samples. The proposed method is rigorously tested on real-world brain MRI segmentation benchmarks, demonstrating superior performance in comparison to existing techniques. Our proposed method achieves an Intersection over Union (IoU) of 95% on the complete Brain MRI Segmentation dataset, demonstrating a 10% improvement over baseline solutions.

PMID:39972098 | DOI:10.1038/s41598-025-90572-5

Sci Rep. 2025 Feb 19;15(1):6029. doi: 10.1038/s41598-025-90084-2.

ABSTRACT

The limited availability of labeled ECG data restricts the application of supervised deep learning methods in ECG detection. Although existing self-supervised learning approaches have been applied to ECG analysis, they are predominantly image-based, which limits their effectiveness. To address these limitations and provide novel insights, we propose a Temporal-Spatial Self-Supervised Learning (TSSL) method specifically designed for ECG detection. TSSL leverages the intrinsic temporal and spatial characteristics of ECG signals to enhance feature representation. Temporally, ECG signals retain consistent identity information over time, enabling the model to generate stable representations for the same individual across different time points while isolating representations of different leads to preserve their unique features. Spatially, ECG signals from various leads capture the heart's activity from different perspectives, revealing both commonalities and distinct patterns. TSSL captures these correlations by maintaining consistency in the relationships between signals and their representations across different leads. Experimental results on the CPSC2018, Chapman, and PTB-XL databases demonstrate that TSSL introduces new capabilities by effectively utilizing temporal and spatial information, achieving superior performance compared to existing methods and approaching the performance of full-label training with only 10% of the labeled data. This highlights TSSL's ability to provide deeper insights and enhanced feature extraction beyond mere performance improvements. We make our code publicly available on https://github.com/cwp9731/temporal-spatial-self-supervised-learning.

PMID:39972080 | DOI:10.1038/s41598-025-90084-2

Sci Rep. 2025 Feb 19;15(1):6116. doi: 10.1038/s41598-025-90418-0.

ABSTRACT

Skin diseases, a significant category in the medical field, have always been challenging to diagnose and have a high misdiagnosis rate. Deep learning for skin disease classification has considerable value in clinical diagnosis and treatment. This study proposes a skin disease classification model based on multi-scale channel attention. The network architecture of the model consists of three main parts: an input module, four processing blocks, and an output module. Firstly, the model has improved the pyramid segmentation attention module to extract multi-scale features of the image entirely. Secondly, the reverse residual structure is used to replace the residual structure in the backbone network, and the attention module is integrated into the reverse residual structure to achieve better multi-scale feature extraction. Finally, the output module consists of an adaptive average pool and a fully connected layer, which convert the aggregated global features into several categories to generate the final output for the classification task. To verify the performance of the proposed model, this study used two commonly used skin disease datasets, ISIC2019 and HAM10000, for validation. The experimental results showed that the accuracy of this study was 77.6% on the ISIC2019 skin disease series dataset and 88.2% on the HAM10000 skin disease dataset. External validation data was added for evaluation to validate the model further, and the comprehensive evaluation results proved the effectiveness of the proposed model in this paper.

PMID:39972014 | DOI:10.1038/s41598-025-90418-0

Sci Rep. 2025 Feb 20;15(1):6132. doi: 10.1038/s41598-025-90530-1.

ABSTRACT

The heart is an important organ that plays a crucial role in maintaining life. Unfortunately, heart disease is one of the major causes of mortality globally. Early and accurate detection can significantly improve the situation by enabling preventive measures and personalized healthcare recommendations. Artificial intelligence is emerging as a powerful tool for healthcare applications, particularly in predicting heart diseases. Researchers are actively working on this, but challenges remain in achieving accurate heart disease prediction. Therefore, experimenting with various models to identify the most effective one for heart disease prediction is crucial. In this view, this paper addresses this need by conducting an extensive investigation of various models. The proposed research considered 11 feature selection techniques and 21 classifiers for the experiment. The feature selection techniques considered for the research are Information Gain, Chi-Square Test, Fisher Discriminant Analysis (FDA), Variance Threshold, Mean Absolute Difference (MAD), Dispersion Ratio, Relief, LASSO, Random Forest Importance, Linear Discriminant Analysis (LDA), and Principal Component Analysis (PCA). The classifiers considered for the research are Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), XGBoost, AdaBoost, Stochastic Gradient Descent (SGD), Gradient Boosting Classifier, Extra Tree Classifier, CatBoost, LightGBM, Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Convolutional Neural Network (CNN), and Hybrid Model (CNN, RNN, LSTM, GRU, BiLSTM, BiGRU). Among all the extensive experiments, XGBoost outperformed all others, achieving an accuracy of 0.97, precision of 0.97, sensitivity of 0.98, specificity of 0.98, F1 score of 0.98, and AUC of 0.98.

PMID:39972004 | DOI:10.1038/s41598-025-90530-1

Sci Rep. 2025 Feb 19;15(1):6062. doi: 10.1038/s41598-025-90768-9.

ABSTRACT

Sand plugging during hydraulic fracturing is one of the primary causes of operational failure. Existing methods for identifying sand plugging during fracturing suffer from issues such as time-consuming, low accuracy, and inability to provide real-time warning. Addressing these challenges, this study leverages offshore hydraulic fracturing operational data and reports to propose a novel method for intelligent identification and real-time warning of sand plugging. Initially, we employ an Attention Mechanism based Long-Short Term Memory Network (Att-LSTM) to establish a real-time pressure prediction model during fracturing, capable of forecasting pressure within 40 s with an accuracy exceeding 92%. Subsequently, we enhance the structure of an Attention Mechanism based Convolutional Long-Short Term Memory Network (Att-CNN-LSTM) to develop a model for identifying sand plugging during fracturing, achieving identification with an error margin of less than 1 min. Finally, through the integration of Att-LSTM and Att-CNN-LSTM networks coupled with transfer learning techniques, we introduce a continuously learning approach for sand plugging warning during fracturing operations, significantly improving accuracy and efficiency in sand plugging identification and advancing the intelligent decision-making process for hydraulic fracturing. These methodologies not only contribute theoretical innovations but also demonstrate substantial practical effectiveness, providing critical technical support and guidance to enhance safety and efficiency in hydraulic fracturing operations.

PMID:39971998 | DOI:10.1038/s41598-025-90768-9

Mol Med. 2025 Feb 19;31(1):63. doi: 10.1186/s10020-025-01119-3.

ABSTRACT

BACKGROUND: As an endoplasmic reticulum (ER) protein, Reticulum 3 (RTN3) has been reported to play a crucial role in neurodegenerative diseases, lipid metabolism, and chronic kidney disease. The involvement of RTN3 in idiopathic pulmonary fibrosis (IPF), a progressive and fatal interstitial lung disease, remains unexplored.

METHODS: In this study, we explored the role of RTN3 in pulmonary fibrosis using public datasets, IPF patient samples, and animal models. We investigated its pathogenic mechanisms in lung fibroblasts and alveolar macrophages.

RESULTS: We found decreased levels of RTN3 in IPF patients, bleomycin-induced mice, and TGFβ-treated cell lines. RTN3-null mice exhibited more severe pulmonary fibrosis phenotypes in old age or after bleomycin treatment. Collagen synthesis was significantly increased in RTN3-null mice lung tissues and lung fibroblasts. Mechanistic studies revealed that RTN3 deficiency reduced the ER-anchored CRTH2 in lung fibroblasts, which serves as an antifibrotic molecule via antagonizing collagen biosynthesis. Simultaneously, RTN3 deficiency reduced the autophagy degradation of CRTH2 which acts as an activator of profibrotic macrophage differentiation. Both effects of RTN3 and CRTH2 in lung fibroblasts and alveolar macrophages aggravated age-or bleomycin-induced pulmonary fibrosis. Additionally, we also identified a mutation of RTN3 in patients with ILD.

CONCLUSIONS: Our research demonstrated that RTN3 plays a significant role in the lung, and reduction of RTN3 levels may be a risk factor for IPF and related diseases.

PMID:39972424 | DOI:10.1186/s10020-025-01119-3